|
In this paper we show how two standard outputs from
<term>
information extraction ( IE ) systems
</term>
-
<term>
named entity annotations
</term>
and
<term>
scenario templates
</term>
- can be used to enhance access to
<term>
text collections
</term>
via a standard
<term>
text browser
</term>
.
We
describe how this information is used in a
<term>
prototype system
</term>
designed to support
<term>
information workers
</term>
' access to a
<term>
pharmaceutical news archive
</term>
as part of their
<term>
industry watch
</term>
function .
|
#313
In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser. We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function. |
|
We describe how this information is used in a
<term>
prototype system
</term>
designed to support
<term>
information workers
</term>
' access to a
<term>
pharmaceutical news archive
</term>
as part of their
<term>
industry watch
</term>
function .
We
also report results of a preliminary ,
<term>
qualitative user evaluation
</term>
of the
<term>
system
</term>
, which while broadly positive indicates further work needs to be done on the
<term>
interface
</term>
to make
<term>
users
</term>
aware of the increased potential of
<term>
IE-enhanced text browsers
</term>
.
|
#344
We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function. We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers. |
|
The purpose of this research is to test the efficacy of applying
<term>
automated evaluation techniques
</term>
, originally devised for the
<term>
evaluation
</term>
of
<term>
human language learners
</term>
, to the
<term>
output
</term>
of
<term>
machine translation ( MT ) systems
</term>
.
We
believe that these
<term>
evaluation techniques
</term>
will provide information about both the
<term>
human language learning process
</term>
, the
<term>
translation process
</term>
and the
<term>
development
</term>
of
<term>
machine translation systems
</term>
.
|
#581
The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems. We believe that these evaluation techniques will provide information about both the human language learning process, the translation process and the development of machine translation systems. |
|
Even more illuminating was the factors on which the
<term>
assessors
</term>
made their decisions .
We
tested this to see if similar criteria could be elicited from duplicating the experiment using
<term>
machine translation output
</term>
.
|
#662
Even more illuminating was the factors on which the assessors made their decisions. We tested this to see if similar criteria could be elicited from duplicating the experiment using machine translation output. |
|
<term>
Listen-Communicate-Show ( LCS )
</term>
is a new paradigm for
<term>
human interaction with data sources
</term>
.
We
integrate a
<term>
spoken language understanding system
</term>
with
<term>
intelligent mobile agents
</term>
that mediate between
<term>
users
</term>
and
<term>
information sources
</term>
.
|
#795
Listen-Communicate-Show (LCS) is a new paradigm for human interaction with data sources. We integrate a spoken language understanding system with intelligent mobile agents that mediate between users and information sources. |
|
We integrate a
<term>
spoken language understanding system
</term>
with
<term>
intelligent mobile agents
</term>
that mediate between
<term>
users
</term>
and
<term>
information sources
</term>
.
We
have built and will demonstrate an application of this approach called
<term>
LCS-Marine
</term>
.
|
#814
We integrate a spoken language understanding system with intelligent mobile agents that mediate between users and information sources. We have built and will demonstrate an application of this approach called LCS-Marine. |
|
<term>
Requestors
</term>
can also instruct the
<term>
system
</term>
to notify them when the status of a
<term>
request
</term>
changes or when a
<term>
request
</term>
is complete .
We
have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this
<term>
technology
</term>
in
<term>
new domains
</term>
.
|
#887
Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete. We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains. |
|
The issue of
<term>
system response
</term>
to
<term>
users
</term>
has been extensively studied by the
<term>
natural language generation community
</term>
, though rarely in the context of
<term>
dialog systems
</term>
.
We
show how research in
<term>
generation
</term>
can be adapted to
<term>
dialog systems
</term>
, and how the high cost of hand-crafting
<term>
knowledge-based generation systems
</term>
can be overcome by employing
<term>
machine learning techniques
</term>
.
|
#995
The issue of system response to users has been extensively studied by the natural language generation community, though rarely in the context of dialog systems. We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques. |
|
In this paper , we address the problem of combining several
<term>
language models ( LMs )
</term>
.
We
find that simple
<term>
interpolation methods
</term>
, like
<term>
log-linear and linear interpolation
</term>
, improve the
<term>
performance
</term>
but fall short of the
<term>
performance
</term>
of an
<term>
oracle
</term>
.
|
#1044
In this paper, we address the problem of combining several language models (LMs). We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of an oracle. |
|
Actually , the
<term>
oracle
</term>
acts like a
<term>
dynamic combiner
</term>
with
<term>
hard decisions
</term>
using the
<term>
reference
</term>
.
We
provide experimental results that clearly show the need for a
<term>
dynamic language model combination
</term>
to improve the
<term>
performance
</term>
further .
|
#1131
Actually, the oracle acts like a dynamic combiner with hard decisions using the reference. We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further. |
|
We provide experimental results that clearly show the need for a
<term>
dynamic language model combination
</term>
to improve the
<term>
performance
</term>
further .
We
suggest a method that mimics the behavior of the
<term>
oracle
</term>
using a
<term>
neural network
</term>
or a
<term>
decision tree
</term>
.
|
#1152
We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further. We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. |
|
The method amounts to tagging
<term>
LMs
</term>
with
<term>
confidence measures
</term>
and picking the best
<term>
hypothesis
</term>
corresponding to the
<term>
LM
</term>
with the best
<term>
confidence
</term>
.
We
describe a three-tiered approach for
<term>
evaluation
</term>
of
<term>
spoken dialogue systems
</term>
.
|
#1195
The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. We describe a three-tiered approach for evaluation of spoken dialogue systems. |
|
The three tiers measure
<term>
user satisfaction
</term>
,
<term>
system support of mission success
</term>
and
<term>
component performance
</term>
.
We
describe our use of this approach in numerous fielded
<term>
user studies
</term>
conducted with the U.S. military .
|
#1223
The three tiers measure user satisfaction, system support of mission success and component performance. We describe our use of this approach in numerous fielded user studies conducted with the U.S. military. |
|
In this paper , we present
<term>
SPoT
</term>
, a
<term>
sentence planner
</term>
, and a new methodology for automatically training
<term>
SPoT
</term>
on the basis of
<term>
feedback
</term>
provided by
<term>
human judges
</term>
.
We
reconceptualize the task into two distinct phases .
|
#1365
In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges. We reconceptualize the task into two distinct phases. |
|
The
<term>
SPR
</term>
uses
<term>
ranking rules
</term>
automatically learned from
<term>
training data
</term>
.
We
show that the trained
<term>
SPR
</term>
learns to select a
<term>
sentence plan
</term>
whose
<term>
rating
</term>
on average is only 5 % worse than the
<term>
top human-ranked sentence plan
</term>
.
|
#1433
The SPR uses ranking rules automatically learned from training data. We show that the trained SPR learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. |
|
In this paper , we compare the relative effects of
<term>
segment order
</term>
,
<term>
segmentation
</term>
and
<term>
segment contiguity
</term>
on the
<term>
retrieval performance
</term>
of a
<term>
translation memory system
</term>
.
We
take a selection of both
<term>
bag-of-words and segment order-sensitive string comparison methods
</term>
, and run each over both
<term>
character - and word-segmented data
</term>
, in combination with a range of
<term>
local segment contiguity models
</term>
( in the form of
<term>
N-grams
</term>
) .
|
#1488
In this paper, we compare the relative effects of segment order, segmentation and segment contiguity on the retrieval performance of a translation memory system. We take a selection of both bag-of-words and segment order-sensitive string comparison methods, and run each over both character- and word-segmented data, in combination with a range of local segment contiguity models (in the form of N-grams). |
|
Further , in their optimum
<term>
configuration
</term>
,
<term>
bag-of-words methods
</term>
are shown to be equivalent to
<term>
segment order-sensitive methods
</term>
in terms of
<term>
retrieval accuracy
</term>
, but much faster .
We
also provide evidence that our findings are scalable .
|
#1587
Further,in their optimum configuration, bag-of-words methods are shown to be equivalent to segment order-sensitive methods in terms of retrieval accuracy, but much faster. We also provide evidence that our findings are scalable. |
|
While
<term>
paraphrasing
</term>
is critical both for
<term>
interpretation and generation of natural language
</term>
, current systems use manual or semi-automatic methods to collect
<term>
paraphrases
</term>
.
We
present an
<term>
unsupervised learning algorithm
</term>
for
<term>
identification of paraphrases
</term>
from a
<term>
corpus of multiple English translations
</term>
of the same
<term>
source text
</term>
.
|
#1777
While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. |
|
The value of this approach is that as the
<term>
operational semantics
</term>
of
<term>
natural language applications
</term>
improve , even larger improvements are possible .
We
provide a
<term>
logical definition
</term>
of
<term>
Minimalist grammars
</term>
, that are
<term>
Stabler 's formalization
</term>
of
<term>
Chomsky 's minimalist program
</term>
.
|
#1926
The value of this approach is that as the operational semantics of natural language applications improve, even larger improvements are possible. We provide a logical definition of Minimalist grammars, that are Stabler's formalization of Chomsky's minimalist program. |
|
In this paper
We
experimentally evaluate a
<term>
trainable sentence planner
</term>
for a
<term>
spoken dialogue system
</term>
by eliciting
<term>
subjective human judgments
</term>
.
|
#2053
In this paper We experimentally evaluate a trainable sentence planner for a spoken dialogue system by eliciting subjective human judgments. |